TY - GEN
T1 - Heart sound anomaly and quality detection using ensemble of neural networks without segmentation
AU - Zabihi, Morteza
AU - Rad, Ali Bahrami
AU - Kiranyaz, Serkan
AU - Gabbouj, Moncef
AU - Katsaggelos, Aggelos K.
N1 - EXT="Rad, Ali Bahrami"
EXT="Kiranyaz, Serkan"
PY - 2017/3/1
Y1 - 2017/3/1
N2 - Phonocardiogram (PCG) signal is used as a diagnostic test in ambulatory monitoring in order to evaluate the heart hemodynamic status and to detect a cardiovascular disease. The objective of this study is to develop an automatic classification method for anomaly (normal vs. abnormal) and quality (good vs. bad) detection of PCG recordings without segmentation. For this purpose, a subset of 18 features is selected among 40 features based on a wrapper feature selection scheme. These features are extracted from time, frequency, and time-frequency domains without any segmentation. The selected features are fed into an ensemble of 20 feedforward neural networks for classification task. The proposed algorithm achieved the overall score of 91.50% (94.23% sensitivity and 88.76% specificity) and 85.90% (86.91% sensitivity and 84.90% specificity) on the train and unseen test datasets, respectively. The proposed method got the second best score in the PhysioNet/CinC Challenge 2016.
AB - Phonocardiogram (PCG) signal is used as a diagnostic test in ambulatory monitoring in order to evaluate the heart hemodynamic status and to detect a cardiovascular disease. The objective of this study is to develop an automatic classification method for anomaly (normal vs. abnormal) and quality (good vs. bad) detection of PCG recordings without segmentation. For this purpose, a subset of 18 features is selected among 40 features based on a wrapper feature selection scheme. These features are extracted from time, frequency, and time-frequency domains without any segmentation. The selected features are fed into an ensemble of 20 feedforward neural networks for classification task. The proposed algorithm achieved the overall score of 91.50% (94.23% sensitivity and 88.76% specificity) and 85.90% (86.91% sensitivity and 84.90% specificity) on the train and unseen test datasets, respectively. The proposed method got the second best score in the PhysioNet/CinC Challenge 2016.
U2 - 10.23919/CIC.2016.7868817
DO - 10.23919/CIC.2016.7868817
M3 - Conference contribution
AN - SCOPUS:85016134921
SP - 613
EP - 616
BT - Computing in Cardiology Conference, CinC 2016
PB - IEEE
T2 - Computing in cardiology conference
Y2 - 1 January 1900
ER -
